Field notes
Short, practical writing on building AI-native systems. Filter by category.
9 posts
- Fundamentalsfundamentals
Model vs harness vs environment
The mental model that separates three different problems people keep conflating when they talk about agents.
Apr 9, 20266 min read - AIadvanced
Reading release notes so you don't have to: Opus 4.6 week
What actually changed in Opus 4.6, what it means for agent builders, and what we changed in production the same day.
Apr 6, 20267 min read - Industrypractitioner
Why we built our own agent harness
Eight months of iteration on a custom harness, what it buys us over off-the-shelf, and where we still use vendor tools.
Apr 2, 20269 min read - Tips & Guidespractitioner
Receipts beat hype: how we log every AI output
If the site says an agent did something, the visitor can see what, how, and when. Here's the schema and the policy.
Mar 28, 20266 min read - Cutting Edgeadvanced
Local inference for SMB: Gemma 4 on a workstation
When running a model on a box under the desk beats paying per token, and when it doesn't.
Mar 18, 20268 min read - Tips & Guidespractitioner
AI readiness for service businesses
A practical way to decide where an agent earns its place in a service operation, and where it doesn't.
Mar 12, 20268 min read - Tips & Guidesfundamentals
Service pages that convert
How to structure a service page so the visitor can decide in 15 seconds whether to keep reading.
Feb 24, 20267 min read - Tips & Guidesfundamentals
Where small businesses actually lose leads
The three handoffs where most SMBs drop paid traffic on the floor, and the smallest fix for each.
Feb 11, 20266 min read - Industryfundamentals
Local SEO operating cadence
A monthly rhythm that balances listings, technical hygiene, and content for a local service business.
Jan 20, 20266 min read
Want the playbooks, not the posts?
Guides are the long-form version. Field-tested writeups you can download and run this week.